[PATCH v13 03/14] eal/linux: add API to set rx interrupt event monitor

[Cunming Liang <cunming.liang@intel.com>]

The patch adds 'rte_intr_rx_ctl' to add or delete interrupt vector events monitor on specified epoll instance.

Signed-off-by: Cunming Liang <cunming.liang@intel.com>
---
v13 changes
 - version map cleanup for v2.1

v12 changes:
 - fix awkward line split in using RTE_LOG

v10 changes:
 - add RTE_INTR_HANDLE_UIO_INTX for uio_pci_generic 

v8 changes
 - fix EWOULDBLOCK and EINTR processing
 - add event status check

v7 changes
 - rename rte_intr_rx_set to rte_intr_rx_ctl.
 - rte_intr_rx_ctl uses rte_epoll_ctl to register epoll event instance.
 - the intr rx event instance includes a intr process callback.

v6 changes
 - split rte_intr_wait_rx_pkt into two function, wait and set.
 - rewrite rte_intr_rx_wait/rte_intr_rx_set to remove queue visibility on eal.
 - rte_intr_rx_wait to support multiplexing.
 - allow epfd as input to support flexible event fd combination.

 lib/librte_eal/linuxapp/eal/eal_interrupts.c       | 101 +++++++++++++++++++++
 .../linuxapp/eal/include/exec-env/rte_interrupts.h |  20 ++++
 lib/librte_eal/linuxapp/eal/rte_eal_version.map    |   1 +
 3 files changed, 122 insertions(+)

diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
index dc327a4..cfe389c 100644
--- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c
+++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
@@ -897,6 +897,49 @@ rte_eal_intr_init(void)
 	return -ret;
 }
 
+static void
+eal_intr_proc_rxtx_intr(int fd, const struct rte_intr_handle *intr_handle)
+{
+	union rte_intr_read_buffer buf;
+	int bytes_read = 1;
+
+	switch (intr_handle->type) {
+	case RTE_INTR_HANDLE_UIO:
+	case RTE_INTR_HANDLE_UIO_INTX:
+		bytes_read = sizeof(buf.uio_intr_count);
+		break;
+#ifdef VFIO_PRESENT
+	case RTE_INTR_HANDLE_VFIO_MSIX:
+	case RTE_INTR_HANDLE_VFIO_MSI:
+	case RTE_INTR_HANDLE_VFIO_LEGACY:
+		bytes_read = sizeof(buf.vfio_intr_count);
+		break;
+#endif
+	default:
+		bytes_read = 1;
+		RTE_LOG(INFO, EAL, "unexpected intr type\n");
+		break;
+	}
+
+	/**
+	 * read out to clear the ready-to-be-read flag
+	 * for epoll_wait.
+	 */
+	do {
+		bytes_read = read(fd, &buf, bytes_read);
+		if (bytes_read < 0) {
+			if (errno == EINTR || errno == EWOULDBLOCK ||
+			    errno == EAGAIN)
+				continue;
+			RTE_LOG(ERR, EAL,
+				"Error reading from fd %d: %s\n",
+				fd, strerror(errno));
+		} else if (bytes_read == 0)
+			RTE_LOG(ERR, EAL, "Read nothing from fd %d\n", fd);
+		return;
+	} while (1);
+}
+
 static int
 eal_epoll_process_event(struct epoll_event *evs, unsigned int n,
 			struct rte_epoll_event *events)
@@ -1033,3 +1076,61 @@ rte_epoll_ctl(int epfd, int op, int fd,
 
 	return 0;
 }
+
+int
+rte_intr_rx_ctl(struct rte_intr_handle *intr_handle, int epfd,
+		int op, unsigned int vec, void *data)
+{
+	struct rte_epoll_event *rev;
+	struct rte_epoll_data *epdata;
+	int epfd_op;
+	int rc = 0;
+
+	if (!intr_handle || intr_handle->nb_efd == 0 ||
+	    vec >= intr_handle->nb_efd) {
+		RTE_LOG(ERR, EAL, "Wrong intr vector number.\n");
+		return -EPERM;
+	}
+
+	switch (op) {
+	case RTE_INTR_EVENT_ADD:
+		epfd_op = EPOLL_CTL_ADD;
+		rev = &intr_handle->elist[vec];
+		if (rev->status != RTE_EPOLL_INVALID) {
+			RTE_LOG(INFO, EAL, "Event already been added.\n");
+			return -EEXIST;
+		}
+
+		/* attach to intr vector fd */
+		epdata = &rev->epdata;
+		epdata->event  = EPOLLIN | EPOLLPRI | EPOLLET;
+		epdata->data   = data;
+		epdata->cb_fun = (rte_intr_event_cb_t)eal_intr_proc_rxtx_intr;
+		epdata->cb_arg = (void *)intr_handle;
+		rc = rte_epoll_ctl(epfd, epfd_op, intr_handle->efds[vec], rev);
+		if (!rc)
+			RTE_LOG(DEBUG, EAL,
+				"efd %d associated with vec %d added on epfd %d"
+				"\n", rev->fd, vec, epfd);
+		else
+			rc = -EPERM;
+		break;
+	case RTE_INTR_EVENT_DEL:
+		epfd_op = EPOLL_CTL_DEL;
+		rev = &intr_handle->elist[vec];
+		if (rev->status == RTE_EPOLL_INVALID) {
+			RTE_LOG(INFO, EAL, "Event does not exist.\n");
+			return -EPERM;
+		}
+
+		rc = rte_epoll_ctl(rev->epfd, epfd_op, rev->fd, rev);
+		if (rc)
+			rc = -EPERM;
+		break;
+	default:
+		RTE_LOG(ERR, EAL, "event op type mismatch\n");
+		rc = -EPERM;
+	}
+
+	return rc;
+}
diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
index 4db95bb..3e93a27 100644
--- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
+++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
@@ -146,4 +146,24 @@ rte_epoll_ctl(int epfd, int op, int fd,
 int
 rte_intr_tls_epfd(void);
 
+/**
+ * @param intr_handle
+ *   Pointer to the interrupt handle.
+ * @param epfd
+ *   Epoll instance fd which the intr vector associated to.
+ * @param op
+ *   The operation be performed for the vector.
+ *   Operation type of {ADD, DEL}.
+ * @param vec
+ *   RX intr vector number added to the epoll instance wait list.
+ * @param data
+ *   User raw data.
+ * @return
+ *   - On success, zero.
+ *   - On failure, a negative value.
+ */
+int
+rte_intr_rx_ctl(struct rte_intr_handle *intr_handle,
+		int epfd, int op, unsigned int vec, void *data);
+
 #endif /* _RTE_LINUXAPP_INTERRUPTS_H_ */
diff --git a/lib/librte_eal/linuxapp/eal/rte_eal_version.map b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
index f388af6..5fb33fa 100644
--- a/lib/librte_eal/linuxapp/eal/rte_eal_version.map
+++ b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
@@ -104,6 +104,7 @@ DPDK_2.1 {
 
 	rte_epoll_ctl;
 	rte_epoll_wait;
+	rte_intr_rx_ctl;
 	rte_intr_tls_epfd;
 
 	local: *;
-- 
1.8.1.4